Better Rewards Yield Better Summaries: Learning to Summarise Without References

September 03, 2019 · Entered Twilight · 🏛 Conference on Empirical Methods in Natural Language Processing

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: LICENSE, README.md, compare_reward.py, data, helpers, outputs, requirements.txt, resources.py, rewarder.py, scorer, step1_encode_doc_summ.py, step2_train_rewarder.py, trained_models

Authors Florian Böhm, Yang Gao, Christian M. Meyer, Ori Shapira, Ido Dagan, Iryna Gurevych arXiv ID 1909.01214 Category cs.CL: Computation & Language Citations 116 Venue Conference on Empirical Methods in Natural Language Processing Repository https://github.com/yg211/summary-reward-no-reference ⭐ 43 Last Checked 1 month ago

Abstract

Reinforcement Learning (RL) based document summarisation systems yield state-of-the-art performance in terms of ROUGE scores, because they directly use ROUGE as the rewards during training. However, summaries with high ROUGE scores often receive low human judgement. To find a better reward function that can guide RL to generate human-appealing summaries, we learn a reward function from human ratings on 2,500 summaries. Our reward function only takes the document and system summary as input. Hence, once trained, it can be used to train RL-based summarisation systems without using any reference summaries. We show that our learned rewards have significantly higher correlation with human ratings than previous approaches. Human evaluation experiments show that, compared to the state-of-the-art supervised-learning systems and ROUGE-as-rewards RL summarisation systems, the RL systems using our learned rewards during training generate summarieswith higher human ratings. The learned reward function and our source code are available at https://github.com/yg211/summary-reward-no-reference.